AdMem: Advanced Memory for Task-solving Agents
Quick Answer
AdMem introduces a unified memory framework for LLMs, integrating semantic, episodic, and procedural memory to enhance task-solving capabilities.
Quick Take
AdMem introduces a unified memory framework for LLMs, integrating semantic, episodic, and procedural memory to enhance task-solving capabilities. This bi-level design improves robustness and success in long multi-turn tasks, demonstrating significant advancements over existing memory approaches.
Key Points
- AdMem combines short-term and long-term memory for enhanced task performance.
- Utilizes a multi-agent architecture for automatic memory generation and retrieval.
- Improvements shown in robustness and success rates across various environments.
- Addresses limitations of prior memory approaches focusing mainly on factual storage.
- Long-term memory management includes reward-based evaluation and pruning.
Article Excerpt
From source RSS / original summaryarXiv:2606. 06787v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability.
We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores. A multi-agent architecture with actor, memory, and critic agents enables automatic memory generation, reward annotation, and adaptive retrieval. Long-term memory is managed through reward-based evaluation, merging, and pruning, ensuring scalability and continual improvement.
Experiments across various environments show that our approach improves robustness and success on long multi-turn tasks compared to existing baselines. This work highlights the importance of comprehensive, adaptive memory for advancing LLM-based agents.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective
This paper addresses the sim-to-real gap for foundation model agents by framing it within a Markov Decision Process (MDP) structure. It advocates for established solutions like domain randomization to enhance agent robustness, aiming to create standardized benchmarks for reliable real-world applications.